Dataset Versions
v4
2024-08-29 6:54am
Generated on Aug 29, 2024
1712 Total Images
View All Images
Dataset Split
Train Set 88%
1512Images
Valid Set 7%
128Images
Test Set 4%
72Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Hue: Between -21° and +21°
Saturation: Between -33% and +33%
Exposure: Between -12% and +12%
Blur: Up to 1.8px
Noise: Up to 0.77% of pixels